CN115983199B - Mobile digital publishing system and method - Google Patents
Mobile digital publishing system and method Download PDFInfo
- Publication number
- CN115983199B CN115983199B CN202310252191.XA CN202310252191A CN115983199B CN 115983199 B CN115983199 B CN 115983199B CN 202310252191 A CN202310252191 A CN 202310252191A CN 115983199 B CN115983199 B CN 115983199B
- Authority
- CN
- China
- Prior art keywords
- target
- published
- picture
- pictures
- content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the field of data identification processing, in particular to a mobile digital publishing system and a method, wherein the system comprises the following steps: the identification module carries out image identification and labeling on the published matters; the analysis module extracts key objects from the images of the picture tags and extracts key words from the images of the content tags, selects correction parameters for the pictures corresponding to the picture tags, and classifies the contents of the corresponding content tags to generate target categories; the processing module carries out picture correction on the picture of the corresponding picture tag image according to the correction parameters, and renders the target picture according to the target rendering parameters obtained by the target category to obtain a picture to be published; the typesetting module typesets the pictures to be published and a plurality of texts to be published, generates inquiry identifications according to names and target categories of the publications to be published, and stores the inquiry identifications in databases of the corresponding categories to generate the target publications. The digital publishing efficiency of the traditional publication is improved through intelligent identification and analysis processing.
Description
Technical Field
The invention relates to the field of data identification processing, in particular to a mobile digital publishing system and a method.
Background
The digital publishing is a publishing form, works of copyrighters are uploaded to electronic equipment through a digital means to meet the needs of audiences, digital auxiliary means are applied in links of creation, editing and processing and the like, the publishing efficiency is greatly improved, the time for the creators to accumulate materials is saved by using a network and a database, and the creation period of the works is shortened.
Chinese patent publication No.: the patent CN105589842B discloses a typesetting method of digital publications, which comprises the following steps: receiving a typesetting instruction sent by a user, wherein the typesetting instruction comprises a classification identifier; determining whether a template file corresponding to the classification identifier exists, wherein the template file is used for describing typesetting layout of the digital publication; if so, displaying the corresponding typesetting layout according to the template file; receiving data to be typeset sent by the user, and loading the data to be typeset to the corresponding position of the typesetting layout to form the digital publication; if not, receiving a template file making instruction sent by the user, and displaying a blank template layout; receiving typesetting layout setting of each layout performed on the blank template layout by the user; extracting template file key information according to the typesetting layout setting, and writing each extracted key information into each corresponding file directory respectively to finish the manufacture of the template file, wherein the template file comprises each file directory, the template file key information comprises typesetting layout information of each layout and attribute information of the template file, and the attribute information comprises the classification identifier.
In the prior art, the typesetting is performed on the data to be typeset of the user according to the typesetting instruction, but the data to be typeset is electronic data, and for publications such as publishing books and newspapers in the traditional publishing mode, manual data input is needed when the publications are subjected to network publishing in the digital publishing mode, so that the digital publishing efficiency of the traditional publications is low.
Disclosure of Invention
Therefore, the invention provides a mobile digital publishing system and a mobile digital publishing method, which can solve the problem of low digital publishing efficiency of the traditional publications.
To achieve the above object, an aspect of the present invention provides a mobile digital publishing system comprising:
the identification module is used for carrying out image identification on the published matters and labeling, and the labels comprise picture labels and a plurality of content labels;
the analysis module is connected with the identification module and used for respectively extracting key objects from the images of the picture tags and extracting key words from the images of the content tags according to a preset key object library and a preset key word library, selecting correction parameters for pictures of the corresponding picture tags according to the extracted key word objects, and classifying the contents of the corresponding content tags according to the extracted key words to generate target categories;
the processing module is connected with the identification module and used for carrying out picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, obtaining target rendering parameters according to the target categories, rendering the target pictures to obtain pictures to be published, and generating a plurality of texts to be published from the pictures of a plurality of content tags;
the typesetting module is connected with the processing module and used for typesetting the pictures to be published and the texts to be published to generate a to-be-published, and generating a query identifier according to the name of the to-be-published and the target category and storing the query identifier in a database of the corresponding category to generate the target publication;
the display module is connected with the typesetting module and used for acquiring a query request of a user, acquiring the corresponding target publication of the database of the corresponding category according to the query identifier in the query request and sending the acquired target publication to a client of the user for display.
Further, when the identification module performs image identification on the published matter, the identification module performs image identification on the published matter according to a preset area to obtain a plurality of images, and tags the images, wherein the tags are keyword information of the preset area.
Further, the analysis module comprises an extraction unit for extracting key objects from the image of the picture tag and extracting key words from the image of the content tag according to a preset key object library and a preset key word library, a selection unit for selecting correction parameters for the corresponding tag image according to the extracted key word objects, and a classification unit for classifying the corresponding tag image according to the extracted key words to generate a tag image category.
Further, when the extraction unit extracts keywords from the images of the content tags, the extraction unit performs text conversion on the images of the content tags to generate texts of the content tags, and the extraction unit performs keyword extraction on the texts of the content tags according to a preset keyword library to obtain keywords;
when classifying the content of the content labels corresponding to the keywords, the classifying unit calculates the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and compares the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, the classification unit judges that the corresponding coincident keywords are target keywords;
if P is less than P0, the classification unit does not judge that the corresponding coincident keywords are target keywords;
the classification unit takes the target keyword as a target category of the text of the corresponding content tag.
Further, after the selection unit selects the correction parameters and the classification unit generates the target categories, the processing module corrects the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, the processing module selects the rendering parameters corresponding to the target categories in a preset rendering parameter library according to the target categories of the texts of the content tags to obtain target rendering parameters, renders the target pictures according to the target rendering parameters to obtain pictures to be published, and the processing module generates a plurality of texts of the content tags to be published.
Further, when typesetting the texts of the pictures to be published and the content labels, the typesetting module sorts the corresponding pictures to be published and the corresponding texts to be published according to a preset typesetting sequence, and sets label links for the pictures to be published and the texts to be published according to the sequence;
and the typesetting module generates a query identifier according to the name of the to-be-published and the target category and stores the query identifier in a database, and stores the to-be-published in the database of the corresponding category according to the target category.
Further, when the obtained target publication is sent to the client of the user to be displayed, the display module obtains the label of the typesetting area of the user terminal of the user, links the label of the typesetting area with the label of the target publication according to the label of the typesetting area, and displays the publication picture of the target publication and a plurality of publication texts which are successfully linked in the typesetting area of the corresponding user terminal;
and when the display module displays the pictures and the texts of the target publication which are successfully linked in the typesetting areas of the corresponding user terminals, acquiring the standard display parameters of the user terminals of the users, and adjusting the pictures and the texts of the target publication according to the standard display parameters so as to display the pictures and the texts in the typesetting areas of the corresponding user terminals.
In another aspect, the present invention also provides a mobile digital publishing method, the method comprising:
carrying out image recognition and labeling on the published matters, wherein the labels comprise picture labels and a plurality of content labels;
an extracting unit for extracting key objects from the images of the picture tags and extracting key words from the images of the content tags according to a preset key object library and a preset key word library, selecting correction parameters for the pictures of the corresponding picture tags according to the extracted key word objects, and classifying the contents of the corresponding content tags according to the extracted key words to generate target categories;
performing picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, rendering the target pictures according to the target class to obtain target rendering parameters to obtain pictures to be published, and generating a plurality of texts to be published from the pictures with a plurality of content tags;
typesetting the pictures to be published and the texts to be published to generate a to-be-published, generating a query identifier according to the names of the to-be-published and the target categories, and storing the query identifier in a database to generate a target publication;
acquiring a query request of a user, acquiring the corresponding target publication of the database according to a query identifier in the query request, and sending the acquired target publication to a client of the user for display.
Further, when keyword extraction is performed on the images of the content tags, performing text conversion on the images of the content tags to generate texts of the content tags, and performing keyword extraction on the texts of the content tags according to a preset keyword library to obtain a plurality of keywords;
when classifying the content according to the keywords as corresponding content labels, calculating the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and comparing the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, judging the corresponding coincident keywords as target keywords;
if P is less than P0, the corresponding coincident keywords are not judged to be target keywords;
and taking the target keyword as a target category of the content of the corresponding content tag.
Further, after the correction parameters are selected and the target categories are generated, picture correction is carried out on pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, the rendering parameters corresponding to the target categories are selected in a preset rendering parameter library according to the target categories of texts of the content tags to obtain target rendering parameters, the target pictures are rendered according to the target rendering parameters to obtain pictures to be published, and texts of a plurality of content tags are generated to form a plurality of texts to be published.
Compared with the prior art, the invention has the advantages that the image recognition and labeling are carried out on the published matters through the recognition module, the uploading of the corresponding area content of the published matters is realized, then the keyword extraction is carried out on the image of the picture label by the analysis module, the keyword extraction is carried out on the image of the content label, the correction parameters are selected according to the extracted keyword object as the picture of the corresponding picture label, the classification is carried out according to the extracted keyword as the content of the corresponding content label, the analysis of the category of the published matters is realized, the picture correction is carried out on the picture according to the correction parameters, the target picture is rendered by the processing module according to the obtained target rendering parameters, the image of a plurality of content labels is generated into a plurality of to-be-published texts, the correction of the picture in the published matters is realized, the color style of the uploaded picture is more clear and accords with the color style of the published matters, the typesetting module typesets the picture to the plurality of to-be-published texts, the query identification is generated and stored in the database, the digital acquisition of the traditional form is finally obtained, the digital form is obtained and the corresponding to the user data is obtained through the acquisition of the client is displayed by the network, the display form is adjusted, the digital form is adjusted to the corresponding to the digital form is displayed by the user's request, the invention is displayed by the display form is adjusted, the target form is displayed by the user through the user terminal, the user terminal is adjusted, the image is displayed by the user terminal is adjusted to the user form, and the user is displayed by the user, and the user is obtained is corresponding to the image is obtained according to the image form and the image is corresponding to the picture and the picture is can and the picture is according to the picture and the picture is can and the picture is, the time of manual input is saved through intelligent identification and analysis processing, and the digital publishing efficiency of the traditional publication is improved.
Drawings
FIG. 1 is a schematic diagram of a mobile digital publishing system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an analysis module of the mobile digital publishing system according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a mobile digital publishing method according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, a mobile digital publishing system according to an embodiment of the present invention includes:
the identification module 110 is used for carrying out image identification on the published matters and labeling, wherein the labels comprise picture labels and a plurality of content labels;
the analysis module 120 is connected with the identification module, and is used for respectively extracting key objects from the image of the picture tag and extracting key words from the image of the content tag according to a preset key object library and a preset key word library, selecting correction parameters for pictures corresponding to the picture tag according to the extracted key word objects, and classifying the contents corresponding to the content tag according to the extracted key words to generate a target category;
the processing module 130 is connected with the identification module and is used for carrying out picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, obtaining target rendering parameters according to the target categories, rendering the target pictures to obtain pictures to be published, and generating a plurality of texts to be published from the pictures of a plurality of content tags;
the typesetting module 140 is connected with the processing module and is used for typesetting the pictures to be published and the texts to be published to generate a to-be-published, and generating a query identifier according to the name of the to-be-published and the target category and storing the query identifier in a database of the corresponding category to generate the target publication;
and the display module 150 is connected with the typesetting module and is used for acquiring the query request of the user, acquiring the corresponding target publication of the database of the corresponding category according to the query identifier in the query request, and sending the acquired target publication to the client of the user for display.
Specifically, the published matter is works which have been published in a conventional form, such as books, periodicals and the like, and the to-be-published matter is a digitally published to-be-published matter; the extracted key object is a key object of a book cover picture, the correction parameter is a correction parameter of the data cover picture, and the label image type is the type of the book content or the field of the book, such as science fiction, suspense and the like.
Specifically, the embodiment of the invention carries out image recognition and labeling on the published object through the recognition module to realize uploading of the content of the corresponding area of the published object, then the analysis module carries out key object extraction on the image of the picture label and keyword extraction on the image of the content label, the correction parameters are selected for the picture corresponding to the picture label according to the extracted keyword object, the classification is carried out according to the content of the content label corresponding to the extracted keyword, the analysis of the category of the published object is realized, then the processing module carries out picture correction on the picture according to the correction parameters, the target picture is rendered by obtaining the target rendering parameters, a plurality of images of the content label are generated into a plurality of texts to be published, the correction of the picture in the published object and the obtaining of the text to be published of the uploaded published object are realized, the invention realizes the network publication of the publications in the traditional form through the digital publishing form by carrying out image recognition, analysis, typesetting and processing on the publications, saves the time of manual input through intelligent recognition and analysis processing, the digital publishing efficiency of the traditional publication is improved.
Specifically, when the identification module performs image identification on the published matter, the identification module performs image identification on the published matter according to a preset area to obtain a plurality of images, and tags the images, wherein the tags are keyword information of the preset area.
Specifically, the preset area may be an area of a book cover, a book introduction, information of a book author, a text of the book, and the corresponding tag content may be a cover, an introduction, an author, a text, and the like.
Specifically, the embodiment of the invention carries out image recognition and labeling on the published matters through the recognition module, so that the uploading of the content of the corresponding area of the published matters is realized, the digital publication of the published matters in the traditional form in the corresponding form is further realized, the time of manual input is saved through intelligent recognition, and the digital publication efficiency of the traditional publication is improved.
Referring to fig. 2, the analysis module includes an extracting unit 121 for extracting a key object from the image of the picture tag and extracting a key word from the image of the content tag according to a preset key object library and a preset key word library, a selecting unit 122 for selecting correction parameters for the corresponding tag image according to the extracted key word object, and a classifying unit 123 for classifying the corresponding tag image according to the extracted key word to generate a tag image category.
Specifically, the extracting unit in the analyzing module of the embodiment of the invention extracts the key object from the image of the picture tag and extracts the key word from the image of the content tag according to the preset key object library and the preset key word library, the selecting unit selects the correction parameters for the picture of the corresponding picture tag according to the extracted key word object, the classifying unit classifies the content of the corresponding content tag according to the extracted key word to generate the target category, so that the category of the published object is analyzed, the picture is further corrected, the picture to be published and a plurality of texts to be published are stored in the database of the corresponding category to realize the network publication of the publication in the traditional publishing form through the digital publishing form, the time of manual input is saved through intelligent recognition and analysis processing, and the digital publishing efficiency of the traditional publication is improved.
Specifically, when the extraction unit extracts keywords from the images of the content tags, the extraction unit performs text conversion on the images of the content tags to generate texts of the content tags, and the extraction unit performs keyword extraction on the texts of the content tags according to a preset keyword library to obtain keywords;
when classifying the content of the content labels corresponding to the keywords, the classifying unit calculates the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and compares the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, the classification unit judges that the corresponding coincident keywords are target keywords;
if P is less than P0, the classification unit does not judge that the corresponding coincident keywords are target keywords;
the classification unit takes the target keyword as a target category of the text of the corresponding content tag.
Specifically, the embodiment of the invention carries out text conversion on images of a plurality of content tags to generate texts of the plurality of content tags through the extraction unit, the extraction unit carries out keyword extraction on the texts of the plurality of content tags according to the preset keyword library to obtain a plurality of keywords, then the classification unit calculates the coincidence rate of the plurality of keywords to judge the corresponding coincident keywords which meet the preset standard as target keywords, classifies the texts of the corresponding content tags according to the target keywords to generate target categories, so that the analysis of the categories of the published matters is realized, further, picture correction is carried out on pictures and query identifications are generated according to names of the to-be-published matters and the target categories and stored in the database, the publication in the traditional publishing form is further subjected to network publishing through the digital publishing form, the time of manual input is saved through intelligent recognition and analysis processing, and the digital publishing efficiency of the traditional publication is improved.
Specifically, after the selection unit selects the correction parameters and the classification unit generates the target categories, the processing module corrects the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, the processing module selects the rendering parameters corresponding to the target categories in a preset rendering parameter library according to the target categories of the texts of the content tags to obtain target rendering parameters, renders the target pictures according to the target rendering parameters to obtain pictures to be published, and the processing module generates a plurality of texts of a plurality of content tags to be published.
Specifically, the picture to be published is a cover picture of the data, and the plurality of texts to be published can be a book brief introduction, an author brief introduction, a book text and the like.
Specifically, when typesetting the texts of the pictures to be published and the content labels, the typesetting module sorts the corresponding pictures to be published and the corresponding texts to be published according to a preset typesetting sequence, and sets label links for the pictures to be published and the texts to be published according to the sequence;
and the typesetting module generates a query identifier according to the name of the to-be-published and the target category and stores the query identifier in a database, and stores the to-be-published in the database of the corresponding category according to the target category.
Specifically, when the obtained target publication is sent to the client of the user to be displayed, the display module obtains the label of the typesetting area of the user terminal of the user, links the label of the typesetting area with the label of the target publication according to the label of the typesetting area, and displays the publication picture and a plurality of publication texts of the target publication which are successfully linked in the typesetting area of the corresponding user terminal;
and when the display module displays the pictures and the texts of the target publication which are successfully linked in the typesetting areas of the corresponding user terminals, acquiring the standard display parameters of the user terminals of the users, and adjusting the pictures and the texts of the target publication according to the standard display parameters so as to display the pictures and the texts in the typesetting areas of the corresponding user terminals.
Specifically, the standard display parameter is a display form of the content of the corresponding typesetting area of the user terminal, for example: font, font size and color of text, etc.
Specifically, the embodiment of the invention obtains the query request of the user through the display module, obtains the corresponding target publication of the database according to the query identifier in the query request, and sends the obtained target publication to the client of the user for display, thereby realizing the display of the digital publication, and automatically adjusting the display form according to the typesetting form of the client to adapt to the display form of the corresponding client, and improving the display effect.
Referring to fig. 3, the method for publishing mobile numbers provided in the embodiment of the present invention includes:
step S210, carrying out image recognition and labeling on the published matters, wherein the labels comprise picture labels and a plurality of content labels;
step S220, an extraction unit for extracting key objects from the images of the picture tags and extracting key words from the images of the content tags respectively according to a preset key object library and a preset key word library, selecting correction parameters for the pictures of the corresponding picture tags according to the extracted key word objects, and classifying the contents of the corresponding content tags according to the extracted key words to generate target categories;
step S230, performing picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, rendering the target pictures according to the target class to obtain pictures to be published, and generating a plurality of texts to be published from the pictures of a plurality of content tags;
step S240, typesetting the picture to be published and the plurality of texts to be published to generate a to-be-published, and generating a query identifier according to the name of the to-be-published and the target category and storing the query identifier in a database to generate a target publication;
step S250, obtaining a query request of a user, obtaining the corresponding target publication of the database according to a query identifier in the query request, and sending the obtained target publication to a client of the user for display.
Specifically, the embodiment of the invention realizes uploading of the content of the corresponding area of the published by carrying out image recognition and labeling on the published, then carrying out key object extraction and keyword extraction on the image of the content label, selecting correction parameters for the picture of the corresponding picture label according to the extracted keyword object, generating a target class according to the extracted keyword, realizing analysis on the class of the published, carrying out picture correction on the picture of the corresponding picture label image according to the correction parameters, carrying out rendering on the target picture according to the target class, generating a plurality of to-be-published texts by the image of a plurality of content labels, realizing correction on the picture in the published and obtaining the to-be-published text content of the uploaded published, leading the uploaded picture to be clearer and more in line with the color of the published, then typesetting the pictures to be published and the plurality of texts to be published to generate a to-be-published, generating a query identifier according to the names of the to-be-published and the target categories, storing the query identifier in a database, realizing digital publication of the published in a traditional form, finally acquiring a query request of a user, acquiring a corresponding target publication of the database according to the query request, transmitting the acquired target publication to a client of the user for displaying, realizing display of the digital publication, automatically adjusting the typesetting form according to the client to adapt to the display form of the corresponding client, improving the display effect, realizing network publication of the published in the traditional form through the digital publication form by carrying out image recognition, analysis, typesetting and processing on the published, the time of manual input is saved through intelligent identification and analysis processing, and the digital publishing efficiency of the traditional publication is improved.
Specifically, when keyword extraction is performed on the images of the content tags, performing text conversion on the images of the content tags to generate texts of the content tags, and performing keyword extraction on the texts of the content tags according to a preset keyword library to obtain a plurality of keywords;
when classifying the content according to the keywords as corresponding content labels, calculating the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and comparing the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, judging the corresponding coincident keywords as target keywords;
if P is less than P0, the corresponding coincident keywords are not judged to be target keywords;
and taking the target keyword as a target category of the content of the corresponding content tag.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A mobile digital publishing system comprising:
the identification module is used for carrying out image identification on the published matters and labeling, and the labels comprise picture labels and a plurality of content labels;
the analysis module is connected with the identification module and used for respectively extracting key objects from the images of the picture tags and extracting key words from the images of the content tags according to a preset key object library and a preset key word library, selecting correction parameters for pictures of the corresponding picture tags according to the extracted key word objects, and classifying the contents of the corresponding content tags according to the extracted key words to generate target categories;
the processing module is connected with the identification module and used for carrying out picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, obtaining target rendering parameters according to the target categories, rendering the target pictures to obtain pictures to be published, and generating a plurality of texts to be published from the pictures of a plurality of content tags;
the typesetting module is connected with the processing module and used for typesetting the pictures to be published and the texts to be published to generate a to-be-published, and generating a query identifier according to the name of the to-be-published and the target category and storing the query identifier in a database of the corresponding category to generate the target publication;
the display module is connected with the typesetting module and used for acquiring a query request of a user, acquiring the corresponding target publication of the database of the corresponding category according to the query identifier in the query request and sending the acquired target publication to a client of the user for display.
2. The mobile digital publishing system of claim 1, wherein the identification module, when performing image recognition on the published material, performs image recognition on the published material according to a preset area to obtain a plurality of images, and tags the plurality of images, wherein the tag is keyword information of the preset area.
3. The mobile digital publishing system of claim 2, wherein the analysis module includes an extraction unit to extract key objects from the image of the picture tag and keyword from the image of the content tag according to a preset key object library and a preset key word library, respectively, a selection unit to select correction parameters for the corresponding tag image according to the extracted key object, and a classification unit to classify the corresponding tag image according to the extracted key word to generate a tag image class.
4. The mobile digital publishing system of claim 3, wherein the extracting unit performs text conversion on the images of the plurality of content tags to generate text of the plurality of content tags when performing keyword extraction on the images of the content tags, and the extracting unit performs keyword extraction on the text of the plurality of content tags according to a preset keyword library to obtain a plurality of keywords;
when classifying the content of the content labels corresponding to the keywords, the classifying unit calculates the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and compares the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, the classification unit judges that the corresponding coincident keywords are target keywords;
if P is less than P0, the classification unit does not judge that the corresponding coincident keywords are target keywords;
the classification unit takes the target keyword as a target category of the text of the corresponding content tag.
5. The mobile digital publishing system of claim 4, wherein after the selection unit selects the correction parameters and the classification unit generates the target categories, the processing module performs picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, the processing module selects the rendering parameters corresponding to the target categories in a preset rendering parameter library according to the target categories of the texts of the content tags to obtain target rendering parameters, renders the target pictures according to the target rendering parameters to obtain pictures to be published, and the processing module generates a plurality of texts of a plurality of content tags to be published.
6. The mobile digital publishing system of claim 5, wherein the typesetting module orders the corresponding pictures to be published and the corresponding texts to be published according to a preset typesetting sequence when typesetting the pictures to be published and the texts of the content labels, and sets label links for the pictures to be published and the texts to be published according to the sequence;
and the typesetting module generates a query identifier according to the name of the to-be-published and the target category and stores the query identifier in a database, and stores the to-be-published in the database of the corresponding category according to the target category.
7. The mobile digital publishing system of claim 6, wherein the display module obtains a label of a typesetting area of a user side of the user when sending the obtained target publication to the user side of the user for display, links the label of the typesetting area with the label of the target publication according to the label of the typesetting area, and displays a publication picture and a plurality of publication texts of the target publication which are successfully linked in the typesetting area of the corresponding user side;
and when the display module displays the pictures and the texts of the target publication which are successfully linked in the typesetting areas of the corresponding user terminals, acquiring the standard display parameters of the user terminals of the users, and adjusting the pictures and the texts of the target publication according to the standard display parameters so as to display the pictures and the texts in the typesetting areas of the corresponding user terminals.
8. A mobile digital publishing method comprising:
carrying out image recognition and labeling on the published matters, wherein the labels comprise picture labels and a plurality of content labels;
extracting key objects from the images of the picture tags and extracting key words from the images of the content tags according to a preset key object library and a preset key word library, selecting correction parameters for the pictures of the corresponding picture tags according to the extracted key word objects, and classifying the contents of the corresponding content tags according to the extracted key words to generate target categories;
performing picture correction on the pictures of the corresponding picture tag images according to the correction parameters to generate target pictures, rendering the target pictures according to the target class to obtain target rendering parameters to obtain pictures to be published, and generating a plurality of texts to be published from the pictures with a plurality of content tags;
typesetting the pictures to be published and the texts to be published to generate a to-be-published, generating a query identifier according to the names of the to-be-published and the target categories, and storing the query identifier in a database to generate a target publication;
acquiring a query request of a user, acquiring the corresponding target publication of the database according to a query identifier in the query request, and sending the acquired target publication to a client of the user for display.
9. The mobile digital publishing method of claim 8, wherein when extracting keywords from the content tagged images, text converting the content tagged images to generate content tagged texts, and extracting keywords from the content tagged texts according to a preset keyword library to obtain keywords;
when classifying the content according to the keywords as corresponding content labels, calculating the coincidence rate P of the keywords, wherein the coincidence rate P=the coincidence number of each type of keywords/the total number of the keywords, and comparing the coincidence rate P with a preset coincidence rate P0;
if P is more than or equal to P0, judging the corresponding coincident keywords as target keywords;
if P is less than P0, the corresponding coincident keywords are not judged to be target keywords;
and taking the target keyword as a target category of the content of the corresponding content tag.
10. The mobile digital publishing method of claim 9, wherein after selecting a correction parameter and generating a target class, performing picture correction on a picture of a corresponding picture tag image according to the correction parameter to generate a target picture, selecting a rendering parameter corresponding to the target class in a preset rendering parameter library according to the target class of the text of the content tag to obtain a target rendering parameter, rendering the target picture according to the target rendering parameter to obtain a picture to be published, and generating a plurality of texts of a plurality of content tags to a plurality of texts to be published.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310252191.XA CN115983199B (en) | 2023-03-16 | 2023-03-16 | Mobile digital publishing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310252191.XA CN115983199B (en) | 2023-03-16 | 2023-03-16 | Mobile digital publishing system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115983199A CN115983199A (en) | 2023-04-18 |
| CN115983199B true CN115983199B (en) | 2023-05-30 |
Family
ID=85976478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310252191.XA Active CN115983199B (en) | 2023-03-16 | 2023-03-16 | Mobile digital publishing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983199B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105589842A (en) * | 2014-11-14 | 2016-05-18 | 北大方正集团有限公司 | Typesetting method and device for digital publications |
Family Cites Families (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8775918B2 (en) * | 2008-10-07 | 2014-07-08 | Visual Software Systems Ltd. | System and method for automatic improvement of electronic presentations |
| JP5474591B2 (en) * | 2010-02-08 | 2014-04-16 | Ｋｄｄｉ株式会社 | Image selection apparatus, image selection method, and image selection program |
| CN103136184B (en) * | 2011-12-05 | 2016-01-13 | 北大方正集团有限公司 | A kind of method of automatic typesetting and device thereof |
| US9098471B2 (en) * | 2011-12-29 | 2015-08-04 | Chegg, Inc. | Document content reconstruction |
| US9736515B1 (en) * | 2012-06-27 | 2017-08-15 | Amazon Technologies, Inc. | Converting digital publications into a format for sending to a user device |
| CN104346615B (en) * | 2013-08-08 | 2019-02-19 | 北大方正集团有限公司 | The extraction element and extracting method of composite diagram in format document |
| CN105159877B (en) * | 2015-06-18 | 2018-02-23 | 杭州电子科技大学 | A kind of across media automatic typesetting systems and its method |
| US20170277663A1 (en) * | 2016-03-24 | 2017-09-28 | Magnificent Marketing LLC | Digital content conversion and publishing system |
| JP2018170653A (en) * | 2017-03-30 | 2018-11-01 | 京セラドキュメントソリューションズ株式会社 | Image forming apparatus and program |
| JP2019021255A (en) * | 2017-07-21 | 2019-02-07 | チャン ホー イン マイケル | Digital publishing system, digital publishing method and computer program |
| CN107544734A (en) * | 2017-08-30 | 2018-01-05 | 咪咕数字传媒有限公司 | A kind of information displaying method, device and storage medium |
| CN110363189B (en) * | 2018-04-09 | 2021-09-24 | 珠海金山办公软件有限公司 | Document content restoration method and device, electronic equipment and readable storage medium |
| CN109272440B (en) * | 2018-08-14 | 2023-11-03 | 阿基米德（上海）传媒有限公司 | Thumbnail generation method and system combining text and image content |
| CN109189985B (en) * | 2018-08-17 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Text style processing method and device, electronic equipment and storage medium |
| CN110390260B (en) * | 2019-06-12 | 2024-03-22 | 平安科技（深圳）有限公司 | Picture scanning piece processing method and device, computer equipment and storage medium |
| CN110807121A (en) * | 2019-09-29 | 2020-02-18 | 广东墨痕教育科技有限公司 | Electronic education resource matching method based on image-text intelligent identification and computer readable storage medium |
| JP2021144275A (en) * | 2020-03-10 | 2021-09-24 | 凸版印刷株式会社 | Image processing system, image processing method, and program |
| CN111814425A (en) * | 2020-07-03 | 2020-10-23 | 角远悠 | Book automatic typesetting implementation method based on book character information |
| JP2022185874A (en) * | 2021-06-03 | 2022-12-15 | 株式会社リコー | Information processing device, information processing system, information processing method, and program |
| CN114429635A (en) * | 2021-12-31 | 2022-05-03 | 深圳云天励飞技术股份有限公司 | Book management method |
| CN114820881A (en) * | 2022-04-12 | 2022-07-29 | 上海商汤智能科技有限公司 | Picture generation method, intelligent terminal and computer readable storage medium thereof |
| CN115270790A (en) * | 2022-08-02 | 2022-11-01 | 安徽云层智能科技有限公司 | Sample identification method, device and medium based on big data |
| CN115601473A (en) * | 2022-10-09 | 2023-01-13 | 《河南科学》杂志社（Cn） | Printed matter typesetting system and method based on intelligent recognition |
-
2023
- 2023-03-16 CN CN202310252191.XA patent/CN115983199B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105589842A (en) * | 2014-11-14 | 2016-05-18 | 北大方正集团有限公司 | Typesetting method and device for digital publications |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115983199A (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160055376A1 (en) | Method and system for identification and extraction of data from structured documents | |
| US6243501B1 (en) | Adaptive recognition of documents using layout attributes | |
| EP0539106B1 (en) | Electronic information delivery system | |
| JP4118349B2 (en) | Document selection method and document server | |
| US5721940A (en) | Form identification and processing system using hierarchical form profiles | |
| US7272269B2 (en) | Image processing apparatus and method therefor | |
| US6275610B1 (en) | File structure for scanned documents | |
| EP0609996A2 (en) | Method and apparatus for creating, indexing and viewing abstracted documents | |
| WO2000052645A1 (en) | Document image processor, method for extracting document title, and method for imparting document tag information | |
| CN105335453B (en) | Image file dividing method | |
| CN110807454B (en) | Text positioning method, device, equipment and storage medium based on image segmentation | |
| US20150278248A1 (en) | Personal Information Management Service System | |
| CN113780229A (en) | Text recognition method and device | |
| JPH08147446A (en) | Electronic filing device | |
| CN109726369A (en) | A kind of intelligent template questions record Implementation Technology based on normative document | |
| CN115983199B (en) | Mobile digital publishing system and method | |
| CN112464907A (en) | Document processing system and method | |
| CN115774805A (en) | File intelligent query method and system based on digital processing | |
| CN113259538B (en) | Electronic file transferring system | |
| JP3319203B2 (en) | Document filing method and apparatus | |
| WO2001013279A2 (en) | Word searchable database from high volume scanning of newspaper data | |
| EP0798653A2 (en) | Method for retrieving an element of an image over a network | |
| CN112800298A (en) | Internet-based electronic commerce data processing method and system | |
| JP3841318B2 (en) | Icon generation method, document search method, and document server | |
| JPH1063813A (en) | Method for managing image document and device therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |